mrp_0.75_seed66_ep2
xlm-roberta-base Finetuning
Model Description
Base Model: xlm-roberta-base
Intermediate Task: mrp-
Pre-Finetuned Model: None
Training Information
Epochs: 2
Steps: 0
Validation Time: 0.01s
Performance Metrics
Main Metrics
Validation Loss: 0.199219
Validation Accuracy: 0.941314
Validation F1: 0.501782
Classification Report
{'0': {'precision': 0.9422229371079298, 'recall': 0.9989086320384707, 'f1-score': 0.96973810548621, 'support': 29321.0}, '1': {'precision': 0.5, 'recall': 0.0175054704595186, 'f1-score': 0.03382663847780127, 'support': 1828.0}, 'accuracy': 0.941314327907798, 'macro avg': {'precision': 0.7211114685539649, 'recall': 0.5082070512489947, 'f1-score': 0.5017823719820056, 'support': 31149.0}, 'weighted avg': {'precision': 0.9162707868291634, 'recall': 0.941314327907798, 'f1-score': 0.9148135120260228, 'support': 31149.0}}
Masked Metrics
Masked Accuracy: 0.937017
Masked F1: 0.497752
Masked Classification Report
{'0': {'precision': 0.937812983702085, 'recall': 0.9990300678952473, 'f1-score': 0.9674540928943784, 'support': 20620.0}, '1': {'precision': 0.5, 'recall': 0.01443001443001443, 'f1-score': 0.028050490883590462, 'support': 1386.0}, 'accuracy': 0.9370171771335091, 'macro avg': {'precision': 0.7189064918510425, 'recall': 0.5067300411626309, 'f1-score': 0.49775229188898445, 'support': 22006.0}, 'weighted avg': {'precision': 0.9102382861009267, 'recall': 0.9370171771335091, 'f1-score': 0.9082878022287895, 'support': 22006.0}}
Trainer Arguments:
"learning_rate": 2e-05
"epochs": 5
"batch_size": 16
"model": xlm-roberta-base
"intermediate_task": mrp
"n_tk_label": 2
"mask_ratio": 0.75
"seed": 66
"dataset": sold
"finetuning_stage": pre
"val_int": 1000
"patience": 3
"skip_empty_rat": True